Elevating News Summarization: Long Short-Term Memory Empowerment for Enriched Content Synthesis in Machine Learning

• Published in: 2023 2nd International Conference on Futuristic Technologies (INCOFT) pp. 1 - 5
• Main Authors: S, Santhosh, S, Sandeep Kumar, M, Ashwin Shenoy, K, Anoop B
• Format: Conference Proceeding
• Language: English
• Published: IEEE 24.11.2023
• Subjects: Data mining; Long short term memory; LSTM-Based Headliner Module; Machine learning; Memory architecture; Natural language processing; Natural Language Processing (NLP); Ranking Algorithm; Recurrent neural networks; Schedules; User-Friendly News Website
• DOI: 10.1109/INCOFT60753.2023.10425546

It's critical to keep up with current happenings in today's fast-paced culture. Due to their hectic schedules, many people, however, find it difficult to keep up with the broad news. To address this issue, we developed a system that effectively summarizes news stories and provides succinct and illuminating summaries. The Text Ranking algorithm is used by our system to extract headline information and produce concise summaries. A headlining module built on a seq-to-seq model and Long Short-Term Memory (LSTM) architecture has also been added. Techniques for Natural Language Processing (NLP) are used to preprocess data and enhance the summary procedure. Recurrent neural networks and LSTM are comparable in that they both excel at capturing longdistance word associations in input sequences. We've created a user-friendly website using these elements to improve accessibility. By empowering people to stay informed without having to read lengthy news pieces, this method responds to the demands of our fast-paced lifestyles.